How to design trait-based analyses of community assembly mechanisms: Insights and guidelines from a literature review

One of the fundamental challenges in ecology is to identify the signature of assembly mechanisms resulting from patterns of community composition. For this purpose, the trait-based approach has promoted the analysis of functional trait distributions within communities. Until now, much attention has been paid to the design of appropriate null models and the definition of relevant functional metrics for inferring community assembly mechanisms from trait distributions. However, less consideration were given to the set of methodological choices preceding the statistical analysis - i.e. from designing a sampling scheme to measuring traits - and how likely they influence the conclusions drawn, as this may subject the analysis to methodological biases. In this regard, a comprehensive perspective on how the overall set of methodological choices influence the inference of community assembly mechanisms is needed. We extensively reviewed recent studies that have addressed animal and plant community assembly by applying a trait-based null model approach. We analyzed how the set of methodological choices in these studies depended on the mechanisms of interest and how they could influence the conclusions drawn by the authors. We found that methodological choices only weakly depended on the hypothesized assembly mechanisms studied by the authors, especially because the two main assembly mechanisms hypothesized, i.e. environmental filtering and limiting similarity, were often tested based on a common experimental design. In contrast, the detection of assembly mechanisms was strongly dependent on the sampling scale, the type of data, the origin of trait values and the delineation of the reference species pool, while less affected by the null model and the functional metrics chosen. These results underline plausible methodological biases in favor of the detection of certain mechanisms to the detriment of others. In addition, there was a significant relationship between the predominant mechanisms concluded by the authors and the type of organism used as biological model, suggesting either that the methodological choices depend on a common strategy used by the different authors when studying similar biological models, or that the methodological choices depended on certain particular properties of the organisms. From this extensive review, we highlight major conceptual and methodological issues that need to be addressed in trait-based null model approaches. We synthesize the methodological choices relevant to study several assembly mechanisms while minimizing methodological biases. We then derive practical guidelines and emphasize the importance of spatial structure in sampling strategy and null model design, because of the scale-dependent signatures of ecological processes. (C) 2017 Elsevier GmbH. All rights reserved.